549 papers with code • 2 benchmarks • 16 datasets
Meta-learning is a methodology considered with "learning to learn" machine learning algorithms.
( Image credit: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks )
Recent progress has demonstrated that such meta-learning methods may exceed scalable human-invented architectures on image classification tasks.
Ranked #3 on Human Part Segmentation on PASCAL-Part
Specifically, we target semi-supervised classification performance, and we meta-learn an algorithm -- an unsupervised weight update rule -- that produces representations useful for this task.
We present Meta Pseudo Labels, a semi-supervised learning method that achieves a new state-of-the-art top-1 accuracy of 90. 2% on ImageNet, which is 1. 6% better than the existing state-of-the-art.
We show that classical gradient-based backpropagation in neural networks can be seen as a special case of a two-state network where one state is used for activations and another for gradients, with update rules derived from the chain rule.
If this is not done, the meta-learner can ignore the task training data and learn a single model that performs all of the meta-training tasks zero-shot, but does not adapt effectively to new image classes.